Robust WLAN Device-free Passive motion detection

Abstract
WLAN Device-free Passive (DfP) localization is an emerging technology that uses the widely deployed WiFi networks for detecting and localizing human presence within indoor environments. This paper presents an accurate and low-overhead technique for detecting human presence based on non-parametric statistical anomaly detection. This technique constructs profiles capturing the signal strength characteristics when no human is present within the area of interest and uses these profiles to identify any anomalies in the signal strength due to human motion activity. To adapt to changes in the environment, the constructed profiles are regularly updated by signal strength readings with low anomaly probability. Exponential smoothing is then used to reduce the effect of noisy readings in order to enhance the detection accuracy. Our work proved to be more robust and accurate than other DfP detection techniques, achieving a high detection accuracy of 4.7% miss detection rate and 3.8% false alarm rate, while requiring minimal deployment overhead.

This publication has 17 references indexed in Scilit: